UAV Trajectory, User Association, and Power Control for Multi-UAV-Enabled Energy-Harvesting Communications: Offline Design and Online Reinforcement Learning

Keyphrases

• Power Control 100%
• UAV 100%
• Vehicle Trajectory 100%
• Multi-UAV 100%
• User Power 100%
• Energy Harvesting Communications 100%
• Interactive Reinforcement Learning 100%
• User Association 100%
• Association Control 100%
• Reinforcement Learning Algorithm 80%
• Channel State Information 40%
• Energy State 40%
• State Information 40%
• Wireless Node 40%
• Information State 40%
• State Channels 40%
• User Rate 40%
• Assisted Reinforcement Learning 40%
• Conventional Reinforcement 40%
• System Performance 20%
• Solar Energy 20%
• Line-of-sight 20%
• Performance Efficiency 20%
• Energy Harvesting 20%
• Learning Systems 20%
• Instantaneous Energy 20%
• Design Problems 20%
• Learning Efficiency 20%
• Environmental Information 20%
• Co-channel Interference 20%
• Uplink 20%
• Finite Time Horizon 20%
• Successive Convex Approximation 20%
• Solar Power 20%
• Nonconvex 20%
• Uplink Power Control 20%
• Futures Knowledge 20%
• Average Energy 20%
• Joint Design 20%
• Non-line-of-sight (NLoS) 20%
• Offline Method 20%
• Convex Optimization 20%
• Alternative Optimization 20%
• Flight Trajectory 20%
• Vehicle Nodes 20%
• Line-of-sight Channel 20%
• Approximation Optimization 20%
• Flight Corridor 20%

Engineering

• Energy Harvesting 100%
• Power Control 100%
• Unmanned Aerial Vehicle 100%
• Reinforcement Learning 100%
• Nodes 37%
• Channel State Information 25%
• Energy State 25%
• State Information 25%
• Energy Engineering 12%
• Systems Performance 12%
• Solar Energy 12%
• Collected Data 12%
• Design Problem 12%
• Channel Interference 12%
• Subproblem 12%
• Finite Time 12%
• Joint Design 12%
• Flight Trajectory 12%

Computer Science

• Reinforcement Learning 100%
• Unmanned Aerial Vehicle 100%
• Channel State Information 25%
• State Information 25%
• wireless node 25%
• Approximation (Algorithm) 12%
• Systems Performance 12%
• Collected Data 12%
• Design Problem 12%
• Environmental Information 12%
• Channel Interference 12%
• Convex Optimization 12%
• Reinforcement Learning-Based Method 12%
• Computational Simulation 12%